Conceptual Combination in Large Language Models: Uncovering Implicit Relational Interpretations in Compound Words With Contextualized Word Embeddings

IF 2.3 2区 心理学 Q2 PSYCHOLOGY, EXPERIMENTAL Cognitive Science Pub Date : 2025-03-13 DOI:10.1111/cogs.70048
Marco Ciapparelli, Calogero Zarbo, Marco Marelli
{"title":"Conceptual Combination in Large Language Models: Uncovering Implicit Relational Interpretations in Compound Words With Contextualized Word Embeddings","authors":"Marco Ciapparelli,&nbsp;Calogero Zarbo,&nbsp;Marco Marelli","doi":"10.1111/cogs.70048","DOIUrl":null,"url":null,"abstract":"<p>Large language models (LLMs) have been proposed as candidate models of human semantics, and as such, they must be able to account for conceptual combination. This work explores the ability of two LLMs, namely, BERT-base and Llama-2-13b, to reveal the implicit meaning of existing and novel compound words. According to psycholinguistic theories, understanding the meaning of a compound (e.g., “snowman”) involves its automatic decomposition into constituent meanings (“snow,” “man”), which are then connected by an implicit semantic relation selected from a set of possible competitors (FOR, <span>MADE</span> <span>OF</span>, BY, …) to obtain a plausible interpretation (“man MADE OF snow”). Here, we leverage the flexibility of LLMs to obtain contextualized representations for both target compounds (e.g., “snowman”) and their implicit interpretations (e.g., “man MADE OF snow”). We demonstrate that replacing a compound with a paraphrased version leads to changes to the embeddings that are inversely proportional to the paraphrase's plausibility, estimated by human raters. While this relation holds for both existing and novel compounds, results obtained for novel compounds are substantially weaker, and older distributional models outperform LLMs. Nonetheless, the present results show that LLMs can offer a valid approximation of the internal structure of compound words posited by cognitive theories, thus representing a promising tool to model word senses that are at once implicit and possible.</p>","PeriodicalId":48349,"journal":{"name":"Cognitive Science","volume":"49 3","pages":""},"PeriodicalIF":2.3000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cognitive Science","FirstCategoryId":"102","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/cogs.70048","RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHOLOGY, EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Large language models (LLMs) have been proposed as candidate models of human semantics, and as such, they must be able to account for conceptual combination. This work explores the ability of two LLMs, namely, BERT-base and Llama-2-13b, to reveal the implicit meaning of existing and novel compound words. According to psycholinguistic theories, understanding the meaning of a compound (e.g., “snowman”) involves its automatic decomposition into constituent meanings (“snow,” “man”), which are then connected by an implicit semantic relation selected from a set of possible competitors (FOR, MADE OF, BY, …) to obtain a plausible interpretation (“man MADE OF snow”). Here, we leverage the flexibility of LLMs to obtain contextualized representations for both target compounds (e.g., “snowman”) and their implicit interpretations (e.g., “man MADE OF snow”). We demonstrate that replacing a compound with a paraphrased version leads to changes to the embeddings that are inversely proportional to the paraphrase's plausibility, estimated by human raters. While this relation holds for both existing and novel compounds, results obtained for novel compounds are substantially weaker, and older distributional models outperform LLMs. Nonetheless, the present results show that LLMs can offer a valid approximation of the internal structure of compound words posited by cognitive theories, thus representing a promising tool to model word senses that are at once implicit and possible.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
Cognitive Science
Cognitive Science PSYCHOLOGY, EXPERIMENTAL-
CiteScore
4.10
自引率
8.00%
发文量
139
期刊介绍: Cognitive Science publishes articles in all areas of cognitive science, covering such topics as knowledge representation, inference, memory processes, learning, problem solving, planning, perception, natural language understanding, connectionism, brain theory, motor control, intentional systems, and other areas of interdisciplinary concern. Highest priority is given to research reports that are specifically written for a multidisciplinary audience. The audience is primarily researchers in cognitive science and its associated fields, including anthropologists, education researchers, psychologists, philosophers, linguists, computer scientists, neuroscientists, and roboticists.
期刊最新文献
Issue Information Conceptual Combination in Large Language Models: Uncovering Implicit Relational Interpretations in Compound Words With Contextualized Word Embeddings Modeling How Suffixes Are Learned in Infancy Opening Social Interactions: The Coordination of Approach, Gaze, Speech, and Handshakes During Greetings Gesture Reduces Mapping Difficulties in the Development of Spatial Language Depending on the Complexity of Spatial Relations
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1